def main(go_file, uniprot_file, filter_exp, prop_annots, cafa_targets,
out_file):
go = Ontology(go_file, with_rels=True)
proteins, accessions, sequences, annotations, interpros, orgs = load_data(
uniprot_file)
df = pd.DataFrame({
'proteins': proteins,
'accessions': accessions,
'sequences': sequences,
'annotations': annotations,
'interpros': interpros,
'orgs': orgs
})
if filter_exp:
logging.info('Filtering proteins with experimental annotations')
index = []
annotations = []
for i, row in enumerate(df.itertuples()):
annots = []
for annot in row.annotations:
go_id, code = annot.split('|')
if is_exp_code(code):
annots.append(go_id)
# Ignore proteins without experimental annotations
if len(annots) == 0:
continue
index.append(i)
annotations.append(annots)
df = df.iloc[index]
df = df.reset_index()
df['annotations'] = annotations
if cafa_targets:
logging.info('Filtering cafa target proteins')
index = []
for i, row in enumerate(df.itertuples()):
if is_cafa_target(row.orgs):
index.append(i)
df = df.iloc[index]
df = df.reset_index()
if prop_annots:
prop_annotations = []
for i, row in df.iterrows():
# Propagate annotations
annot_set = set()
annots = row['annotations']
for go_id in annots:
go_id = go_id.split('|')[0] # In case if it has code
annot_set |= go.get_anchestors(go_id)
annots = list(annot_set)
prop_annotations.append(annots)
df['annotations'] = prop_annotations
df.to_pickle(out_file)
logging.info('Successfully saved %d proteins' % (len(df), ))
def main(go_file, swissprot_file, out_file):
go = Ontology(go_file, with_rels=True)
if swissprot_file.endswith("gz"):
proteins, accessions, sequences, annotations, interpros, orgs = load_data_gzip(
swissprot_file)
else:
proteins, accessions, sequences, annotations, interpros, orgs = load_data(
swissprot_file)
df = pd.DataFrame({
'proteins': proteins,
'accessions': accessions,
'sequences': sequences,
'annotations': annotations,
'interpros': interpros,
'orgs': orgs
})
logging.info('Filtering proteins with experimental annotations')
index = []
annotations = []
for i, row in enumerate(df.itertuples()):
annots = []
for annot in row.annotations:
go_id, code = annot.split('|')
if is_exp_code(code):
annots.append(go_id)
# Ignore proteins without experimental annotations
if len(annots) == 0:
continue
index.append(i)
annotations.append(annots)
df = df.iloc[index]
df = df.reset_index()
df['exp_annotations'] = annotations
prop_annotations = []
for i, row in df.iterrows():
# Propagate annotations
annot_set = set()
annots = row['exp_annotations']
for go_id in annots:
annot_set |= go.get_anchestors(go_id)
annots = list(annot_set)
prop_annotations.append(annots)
df['prop_annotations'] = prop_annotations
cafa_target = []
for i, row in enumerate(df.itertuples()):
if is_cafa_target(row.orgs):
cafa_target.append(True)
else:
cafa_target.append(False)
df['cafa_target'] = cafa_target
df.to_pickle(out_file)
logging.info('Successfully saved %d proteins' % (len(df), ))
def main(go_file, uniprot_file, filter_exp, prop_annots, out_file):
go = Ontology(go_file, with_rels=True)
proteins, accessions, sequences, annotations, interpros, orgs, genes, gene_names = load_data(uniprot_file)
df = pd.DataFrame({
'proteins': proteins,
'accessions': accessions,
'sequences': sequences,
'annotations': annotations,
'interpros': interpros,
'orgs': orgs,
'genes': genes,
'gene_names': gene_names
})
# Filter proteins
df = df[df['orgs'] == '9606']
logging.info('Filtering proteins with experimental annotations')
index = []
annotations = []
iea_annotations = []
for i, row in enumerate(df.itertuples()):
annots = set()
iea_annots = set()
for annot in row.annotations:
go_id, code = annot.split('|')
anch_set = go.get_anchestors(go_id)
if is_exp_code(code):
annots |= anch_set
iea_annots |= anch_set
annots = list(annots)
iea_annots = list(iea_annots)
annotations.append(annots)
iea_annotations.append(iea_annots)
df['exp_annotations'] = annotations
df['iea_annotations'] = iea_annotations
df.to_pickle(out_file)
logging.info('Successfully saved %d proteins' % (len(df),) )
def main(train_data_file, test_data_file, diamond_scores_file, ont):
go_rels = Ontology('data/go.obo', with_rels=True)
train_df = pd.read_pickle(train_data_file)
annotations = train_df['prop_annotations'].values
annotations = list(map(lambda x: set(x), annotations))
test_df = pd.read_pickle(test_data_file)
test_annotations = test_df['prop_annotations'].values
test_annotations = list(map(lambda x: set(x), test_annotations))
go_rels.calculate_ic(annotations + test_annotations)
prot_index = {}
for i, row in enumerate(train_df.itertuples()):
prot_index[row.proteins] = i
# BLAST Similarity (Diamond)
diamond_scores = {}
with open(diamond_scores_file) as f:
for line in f:
it = line.strip().split()
if it[0] not in diamond_scores:
diamond_scores[it[0]] = {}
diamond_scores[it[0]][it[1]] = float(it[2])
blast_preds = []
for i, row in enumerate(test_df.itertuples()):
annots = {}
prot_id = row.proteins
# BlastKNN
if prot_id in diamond_scores:
sim_prots = diamond_scores[prot_id]
allgos = set()
total_score = 0.0
for p_id, score in sim_prots.items():
allgos |= annotations[prot_index[p_id]]
total_score += score
allgos = list(sorted(allgos))
sim = np.zeros(len(allgos), dtype=np.float32)
for j, go_id in enumerate(allgos):
s = 0.0
for p_id, score in sim_prots.items():
if go_id in annotations[prot_index[p_id]]:
s += score
sim[j] = s / total_score
for go_id, score in zip(allgos, sim):
annots[go_id] = score
blast_preds.append(annots)
go_set = go_rels.get_namespace_terms(NAMESPACES[ont])
go_set.remove(FUNC_DICT[ont])
labels = test_annotations
labels = list(map(lambda x: set(filter(lambda y: y in go_set, x)), labels))
print(len(go_set))
fmax = 0.0
tmax = 0.0
smin = 1000.0
precisions = []
recalls = []
for t in range(101):
threshold = t / 100.0
preds = []
for i, row in enumerate(test_df.itertuples()):
annots = set()
for go_id, score in blast_preds[i].items():
if score >= threshold:
annots.add(go_id)
new_annots = set()
for go_id in annots:
new_annots |= go_rels.get_anchestors(go_id)
preds.append(new_annots)
# Filter classes
preds = list(
map(lambda x: set(filter(lambda y: y in go_set, x)), preds))
fscore, prec, rec, s = evaluate_annotations(go_rels, labels, preds)
precisions.append(prec)
recalls.append(rec)
print(f'Fscore: {fscore}, S: {s}, threshold: {threshold}')
if fmax < fscore:
fmax = fscore
tmax = threshold
if smin > s:
smin = s
print(f'Fmax: {fmax:0.3f}, Smin: {smin:0.3f}, threshold: {tmax}')
precisions = np.array(precisions)
recalls = np.array(recalls)
sorted_index = np.argsort(recalls)
recalls = recalls[sorted_index]
precisions = precisions[sorted_index]
aupr = np.trapz(precisions, recalls)
print(f'AUPR: {aupr:0.3f}')
plt.figure()
lw = 2
plt.plot(recalls,
precisions,
color='darkorange',
lw=lw,
label=f'AUPR curve (area = {aupr:0.3f})')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('Recall')
plt.ylabel('Precision')
plt.title('Area Under the Precision-Recall curve')
plt.legend(loc="lower right")
plt.savefig('aupr.pdf')
plt.show()
def main(train_data_file, test_data_file, out_file, terms_file, root_class, fold):
# Cross validation evaluation
out_file = f'fold{fold}_' + out_file
test_data_file = f'fold{fold}_' + test_data_file
hp = Ontology('data/hp.obo', with_rels=True)
terms_df = pd.read_pickle(terms_file)
terms = terms_df['terms'].values.flatten()
terms_dict = {v: i for i, v in enumerate(terms)}
train_df = pd.read_pickle(train_data_file)
naive_annots = {}
for i, row in train_df.iterrows():
for hp_id in row.hp_annotations:
if hp_id in naive_annots:
naive_annots[hp_id] += 1
else:
naive_annots[hp_id] = 1
for hp_id in naive_annots:
naive_annots[hp_id] /= 1.0 * len(train_df)
test_df = pd.read_pickle(test_data_file)
annotations = train_df['hp_annotations'].values
annotations = list(map(lambda x: set(x), annotations))
test_annotations = test_df['hp_annotations'].values
test_annotations = list(map(lambda x: set(x), test_annotations))
hp.calculate_ic(annotations)
hp_set = set(terms)
all_classes = hp.get_term_set(root_class)
hp_set = hp_set.intersection(all_classes)
hp_set.discard(root_class)
print(len(hp_set))
labels = test_annotations
labels = list(map(lambda x: set(filter(lambda y: y in hp_set, x)), labels))
# Compute AUC
auc_terms = list(hp_set)
auc_terms_dict = {v: i for i, v in enumerate(auc_terms)}
auc_preds = np.zeros((len(test_df), len(hp_set)), dtype=np.float32)
auc_labels = np.zeros((len(test_df), len(hp_set)), dtype=np.int32)
for i in range(len(labels)):
for j, hp_id in enumerate(auc_terms):
auc_preds[i, j] = naive_annots[hp_id]
if hp_id in labels[i]:
auc_labels[i, j] = 1
# Compute macro AUROC
roc_auc = 0.0
total = 0
for i, hp_id in enumerate(auc_terms):
if np.sum(auc_labels[:, i]) == 0:
continue
total += 1
auc = compute_roc(auc_labels[:, i], auc_preds[:, i])
if not math.isnan(auc):
roc_auc += auc
else:
roc_auc += 1
roc_auc /= total
print(roc_auc)
return
fmax = 0.0
tmax = 0.0
pmax = 0.0
rmax = 0.0
precisions = []
recalls = []
smin = 1000000.0
max_preds = None
for t in range(0, 101):
threshold = t / 100.0
gene_id = row.genes
annots = set()
for hp_id, score in naive_annots.items():
if score >= threshold:
annots.add(hp_id)
new_annots = set()
for hp_id in annots:
new_annots |= hp.get_anchestors(hp_id)
preds = []
for i, row in enumerate(test_df.itertuples()):
preds.append(new_annots)
# Filter classes
fscore, prec, rec, s = evaluate_annotations(hp, labels, preds)
precisions.append(prec)
recalls.append(rec)
print(f'Fscore: {fscore}, S: {s}, threshold: {threshold}')
if fmax < fscore:
fmax = fscore
tmax = threshold
pmax = prec
rmax = rec
max_preds = preds
if smin > s:
smin = s
test_df['hp_preds'] = max_preds
test_df.to_pickle(out_file)
precisions = np.array(precisions)
recalls = np.array(recalls)
sorted_index = np.argsort(recalls)
recalls = recalls[sorted_index]
precisions = precisions[sorted_index]
aupr = np.trapz(precisions, recalls)
print(f'AUROC: {roc_auc:0.3f}, AUPR: {aupr:0.3f}, Fmax: {fmax:0.3f}, Prec: {pmax:0.3f}, Rec: {rmax:0.3f}, Smin: {smin:0.3f}, threshold: {tmax}')
def main(train_data_file, test_data_file, terms_file, out_file, root_class,
fold):
# Cross validation evaluation
out_file = f'fold{fold}_' + out_file
test_data_file = f'fold{fold}_' + test_data_file
hp = Ontology('data/hp.obo', with_rels=True)
terms_df = pd.read_pickle(terms_file)
terms = terms_df['terms'].values.flatten()
terms_dict = {v: i for i, v in enumerate(terms)}
train_df = pd.read_pickle(train_data_file)
test_df = pd.read_pickle(test_data_file)
annotations = train_df['hp_annotations'].values
annotations = list(map(lambda x: set(x), annotations))
test_annotations = test_df['hp_annotations'].values
test_annotations = list(map(lambda x: set(x), test_annotations))
hp.calculate_ic(annotations)
hp_set = set(terms)
all_classes = hp.get_term_set(root_class)
hp_set = hp_set.intersection(all_classes)
hp_set.discard(root_class)
print(len(hp_set))
labels = test_annotations
labels = list(map(lambda x: set(filter(lambda y: y in hp_set, x)), labels))
# Compute AUC
auc_terms = list(hp_set)
auc_terms_dict = {v: i for i, v in enumerate(auc_terms)}
auc_preds = np.zeros((len(test_df), len(hp_set)), dtype=np.float32)
auc_labels = np.zeros((len(test_df), len(hp_set)), dtype=np.int32)
for i, row in enumerate(test_df.itertuples()):
for j, hp_id in enumerate(auc_terms):
auc_preds[i, j] = row.preds[terms_dict[hp_id]]
if hp_id in labels[i]:
auc_labels[i, j] = 1
# Compute macro AUROC
roc_auc = 0.0
total = 0
for i, hp_id in enumerate(auc_terms):
if np.sum(auc_labels[:, i]) == 0:
continue
total += 1
auc = compute_roc(auc_labels[:, i], auc_preds[:, i])
if not math.isnan(auc):
roc_auc += auc
else:
roc_auc += 1
roc_auc /= total
print(roc_auc)
return
fmax = 0.0
tmax = 0.0
pmax = 0.0
rmax = 0.0
precisions = []
recalls = []
smin = 1000000.0
max_preds = None
for t in range(0, 101):
threshold = t / 100.0
preds = []
for i, row in enumerate(test_df.itertuples()):
gene_id = row.genes
annots_dict = {}
for j, score in enumerate(row.preds):
hp_id = terms[j]
# score = score * (1 - alpha)
if hp_id in annots_dict:
annots_dict[hp_id] += score
else:
annots_dict[hp_id] = score
annots = set()
for hp_id, score in annots_dict.items():
if score >= threshold:
annots.add(hp_id)
new_annots = set()
for hp_id in annots:
new_annots |= hp.get_anchestors(hp_id)
new_annots = new_annots.intersection(hp_set)
preds.append(new_annots)
# Filter classes
fscore, prec, rec, s = evaluate_annotations(hp, labels, preds)
precisions.append(prec)
recalls.append(rec)
print(f'Fscore: {fscore}, S: {s}, threshold: {threshold}')
if fmax < fscore:
fmax = fscore
tmax = threshold
max_preds = preds
pmax = prec
rmax = rec
if smin > s:
smin = s
test_df['hp_preds'] = max_preds
test_df.to_pickle(out_file)
precisions = np.array(precisions)
recalls = np.array(recalls)
sorted_index = np.argsort(recalls)
recalls = recalls[sorted_index]
precisions = precisions[sorted_index]
aupr = np.trapz(precisions, recalls)
print(
f'AUROC: {roc_auc:0.3f}, AUPR: {aupr:0.3f}, Fmax: {fmax:0.3f}, Prec: {pmax:0.3f}, Rec: {rmax:0.3f}, Smin: {smin:0.3f}, threshold: {tmax}'
)
plt.figure()
lw = 2
plt.plot(recalls,
precisions,
color='darkorange',
lw=lw,
label=f'AUPR curve (area = {aupr:0.2f})')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('Recall')
plt.ylabel('Precision')
plt.title('Area Under the Precision-Recall curve')
plt.legend(loc="lower right")
df = pd.DataFrame({'precisions': precisions, 'recalls': recalls})
def main(train_data_file, test_data_file, terms_file, diamond_scores_file, ont,
alpha):
alpha /= 100.0
go_rels = Ontology('data-cafa/go.obo', with_rels=True)
terms_df = pd.read_pickle(terms_file)
terms = terms_df['terms'].values.flatten()
terms_dict = {v: i for i, v in enumerate(terms)}
train_df = pd.read_pickle(train_data_file)
test_df = pd.read_pickle(test_data_file)
annotations = train_df['annotations'].values
annotations = list(map(lambda x: set(x), annotations))
test_annotations = test_df['annotations'].values
test_annotations = list(map(lambda x: set(x), test_annotations))
go_rels.calculate_ic(annotations + test_annotations)
# Print IC values of terms
ics = {}
for term in terms:
ics[term] = go_rels.get_ic(term)
prot_index = {}
for i, row in enumerate(train_df.itertuples()):
prot_index[row.proteins] = i
# BLAST Similarity (Diamond)
diamond_scores = {}
with open(diamond_scores_file) as f:
for line in f:
it = line.strip().split()
if it[0] not in diamond_scores:
diamond_scores[it[0]] = {}
diamond_scores[it[0]][it[1]] = float(it[2])
blast_preds = []
for i, row in enumerate(test_df.itertuples()):
annots = {}
prot_id = row.proteins
# BlastKNN
if prot_id in diamond_scores:
sim_prots = diamond_scores[prot_id]
allgos = set()
total_score = 0.0
for p_id, score in sim_prots.items():
allgos |= annotations[prot_index[p_id]]
total_score += score
allgos = list(sorted(allgos))
sim = np.zeros(len(allgos), dtype=np.float32)
for j, go_id in enumerate(allgos):
s = 0.0
for p_id, score in sim_prots.items():
if go_id in annotations[prot_index[p_id]]:
s += score
sim[j] = s / total_score
ind = np.argsort(-sim)
for go_id, score in zip(allgos, sim):
annots[go_id] = score
blast_preds.append(annots)
# DeepGOPlus
go_set = go_rels.get_namespace_terms(NAMESPACES[ont])
go_set.remove(FUNC_DICT[ont])
labels = test_df['annotations'].values
labels = list(map(lambda x: set(filter(lambda y: y in go_set, x)), labels))
# print(len(go_set))
deep_preds = []
alphas = {
NAMESPACES['mf']: 0.55,
NAMESPACES['bp']: 0.59,
NAMESPACES['cc']: 0.46
}
for i, row in enumerate(test_df.itertuples()):
annots_dict = blast_preds[i].copy()
for go_id in annots_dict:
annots_dict[go_id] *= alphas[go_rels.get_namespace(go_id)]
for j, score in enumerate(row.preds):
go_id = terms[j]
score *= 1 - alphas[go_rels.get_namespace(go_id)]
if go_id in annots_dict:
annots_dict[go_id] += score
else:
annots_dict[go_id] = score
deep_preds.append(annots_dict)
print('AUTHOR DeepGOPlus')
print('MODEL 1')
print('KEYWORDS sequence alignment.')
for i, row in enumerate(test_df.itertuples()):
prot_id = row.proteins
for go_id, score in deep_preds[i].items():
print(f'{prot_id}\t{go_id}\t{score:.2f}')
print('END')
return
# Propagate scores
# deepgo_preds = []
# for annots_dict in deep_preds:
# annots = {}
# for go_id, score in annots_dict.items():
# for a_id in go_rels.get_anchestors(go_id):
# if a_id in annots:
# annots[a_id] = max(annots[a_id], score)
# else:
# annots[a_id] = score
# deepgo_preds.append(annots)
fmax = 0.0
tmax = 0.0
precisions = []
recalls = []
smin = 1000000.0
rus = []
mis = []
for t in range(0, 101):
threshold = t / 100.0
preds = []
for i, row in enumerate(test_df.itertuples()):
annots = set()
for go_id, score in deep_preds[i].items():
if score >= threshold:
annots.add(go_id)
new_annots = set()
for go_id in annots:
new_annots |= go_rels.get_anchestors(go_id)
preds.append(new_annots)
# Filter classes
preds = list(
map(lambda x: set(filter(lambda y: y in go_set, x)), preds))
fscore, prec, rec, s, ru, mi, fps, fns = evaluate_annotations(
go_rels, labels, preds)
avg_fp = sum(map(lambda x: len(x), fps)) / len(fps)
avg_ic = sum(
map(lambda x: sum(map(lambda go_id: go_rels.get_ic(go_id), x)),
fps)) / len(fps)
print(f'{avg_fp} {avg_ic}')
precisions.append(prec)
recalls.append(rec)
print(
f'Fscore: {fscore}, Precision: {prec}, Recall: {rec} S: {s}, RU: {ru}, MI: {mi} threshold: {threshold}'
)
if fmax < fscore:
fmax = fscore
tmax = threshold
if smin > s:
smin = s
print(f'Fmax: {fmax:0.3f}, Smin: {smin:0.3f}, threshold: {tmax}')
precisions = np.array(precisions)
recalls = np.array(recalls)
sorted_index = np.argsort(recalls)
recalls = recalls[sorted_index]
precisions = precisions[sorted_index]
aupr = np.trapz(precisions, recalls)
print(f'AUPR: {aupr:0.3f}')
plt.figure()
lw = 2
plt.plot(recalls,
precisions,
color='darkorange',
lw=lw,
label=f'AUPR curve (area = {aupr:0.2f})')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('Recall')
plt.ylabel('Precision')
plt.title('Area Under the Precision-Recall curve')
plt.legend(loc="lower right")
plt.savefig(f'aupr_{ont}_{alpha:0.2f}.pdf')
df = pd.DataFrame({'precisions': precisions, 'recalls': recalls})
df.to_pickle(f'PR_{ont}_{alpha:0.2f}.pkl')
def main(go_file, mp_file, mp_annots_file, deepgo_annots_file, id_mapping_file,
data_file, out_data_file, out_terms_file, min_count):
go = Ontology(go_file, with_rels=True)
logging.info('GO loaded')
mp = Ontology(mp_file, with_rels=True)
logging.info('MP loaded')
logging.info('Load MP2Uniprot mapping')
prot2gene = {}
with open(id_mapping_file) as f:
next(f)
for line in f:
it = line.strip().split('\t')
if it[0] not in gene2prot:
gene2prot[it[0]] = []
gene2prot[it[0]] += list(it[6].split())
logging.info('Loading MP annotations')
mp_annots = {}
df = pd.read_pickle(data_file)
acc2prot = {}
for row in df.itertuples():
p_id = row.proteins
acc_ids = row.accessions.split('; ')
for acc_id in acc_ids:
acc2prot[acc_id] = p_id
with open(mp_annots_file) as f:
next(f)
for line in f:
it = line.strip().split('\t')
for mgi in it[6].split('|'):
if mgi not in gene2prot:
continue
prot_ids = gene2prot[mgi]
mp_id = it[4]
for prot_id in prot_ids:
if prot_id not in acc2prot:
continue
prot_id = acc2prot[prot_id]
if prot_id not in mp_annots:
mp_annots[prot_id] = set()
if mp.has_term(mp_id):
mp_annots[prot_id] |= mp.get_anchestors(mp_id)
print('MP Annotations', len(mp_annots))
dg_annots = {}
gos = set()
with open(deepgo_annots_file) as f:
for line in f:
it = line.strip().split('\t')
prot_id = it[0]
annots = []
for item in it[1:]:
go_id, score = item.split('|')
score = float(score)
annots.append(go_id)
dg_annots[prot_id] = it[1:]
gos |= set(annots)
print('DeepGO Annotations', len(dg_annots))
print('Number of GOs', len(gos))
go_df = pd.DataFrame({'gos': list(gos)})
go_df.to_pickle('data/gos.pkl')
logging.info('Processing annotations')
cnt = Counter()
annotations = list()
for prot_id, annots in mp_annots.items():
for term in annots:
cnt[term] += 1
deepgo_annots = []
go_annots = []
mpos = []
prots = []
sequences = []
for row in df.itertuples():
p_id = row.proteins
if p_id in mp_annots:
prots.append(p_id)
mpos.append(mp_annots[p_id])
go_annots.append(row.annotations)
deepgo_annots.append(dg_annots[p_id])
sequences.append(row.sequences)
prots_set = set(prots)
for key, val in mp_annots.items():
if key not in prots_set:
print(key)
df = pd.DataFrame({
'proteins': prots,
'mp_annotations': mpos,
'go_annotations': go_annots,
'deepgo_annotations': deepgo_annots,
'sequences': sequences
})
df.to_pickle(out_data_file)
print(f'Number of proteins {len(df)}')
# Filter terms with annotations more than min_count
res = {}
for key, val in cnt.items():
if key == 'MP:0000001':
continue
if val >= min_count:
ont = key.split(':')[0]
if ont not in res:
res[ont] = []
res[ont].append(key)
terms = []
for key, val in res.items():
print(key, len(val))
terms += val
logging.info(f'Number of terms {len(terms)}')
# Save the list of terms
df = pd.DataFrame({'terms': terms})
df.to_pickle(out_terms_file)
def helper(train_df, test_df, ont):
go = Ontology('data-cafa/go.obo', with_rels=True)
terms_df = pd.read_pickle('data-cafa/' + ont + '.pkl')
terms = terms_df['functions'].values.flatten()
terms_dict = {v: i for i, v in enumerate(terms)}
train_df = train_df.rename(columns={"gos": "annotations"})
annotations = train_df['annotations'].values
annotations = list(map(lambda x: set(x), annotations))
test_df = test_df.rename(columns={"gos": "annotations"})
# Annotations
test_annotations = []
for i, row in enumerate(test_df.itertuples()):
annots = set()
for go_id in row.annotations:
if go.has_term(go_id):
annots |= go.get_anchestors(go_id)
test_annotations.append(annots)
go.calculate_ic(annotations + test_annotations)
prot_index = {}
for i, row in enumerate(train_df.itertuples()):
prot_index[row.proteins] = i
# DeepGO
go_set = go.get_namespace_terms(NAMESPACES[ont])
go_set.remove(FUNC_DICT[ont])
labels = test_annotations
labels = list(map(lambda x: set(filter(lambda y: y in go_set, x)), labels))
print(len(go_set))
fmax = 0.0
tmax = 0.0
smin = 1000.0
precisions = []
recalls = []
for t in range(1, 101):
threshold = t / 100.0
preds = []
for i, row in enumerate(test_df.itertuples()):
annots = set()
for j, score in enumerate(row.predictions):
if score >= threshold:
annots.add(terms[j])
new_annots = set()
for go_id in annots:
new_annots |= go.get_anchestors(go_id)
preds.append(new_annots)
# Filter classes
preds = list(
map(lambda x: set(filter(lambda y: y in go_set, x)), preds))
fscore, prec, rec, s = evaluate_annotations(go, labels, preds)
precisions.append(prec)
recalls.append(rec)
print('Fscore: {}, S: {}, threshold: {}'.format(fscore, s, threshold))
if fmax < fscore:
fmax = fscore
tmax = threshold
if smin > s:
smin = s
print('Fmax: {:0.3f}, Smin: {:0.3f}, threshold: {}'.format(
fmax, smin, tmax))
precisions = np.array(precisions)
recalls = np.array(recalls)
sorted_index = np.argsort(recalls)
recalls = recalls[sorted_index]
precisions = precisions[sorted_index]
aupr = np.trapz(precisions, recalls)
print('AUPR: {:0.3f}'.format(aupr))
return [recalls, precisions, aupr]
def main(train_data_file, valid_data_file, terms_file, diamond_scores_file,
ont):
go_rels = Ontology('data-cafa/go.obo', with_rels=True)
terms_df = pd.read_pickle(terms_file)
terms = terms_df['terms'].values.flatten()
terms_dict = {v: i for i, v in enumerate(terms)}
train_df = pd.read_pickle(train_data_file)
valid_df = pd.read_pickle(valid_data_file)
annotations = train_df['annotations'].values
annotations = list(map(lambda x: set(x), annotations))
valid_annotations = valid_df['annotations'].values
valid_annotations = list(map(lambda x: set(x), valid_annotations))
go_rels.calculate_ic(annotations + valid_annotations)
# Print IC values of terms
ics = {}
for term in terms:
ics[term] = go_rels.get_ic(term)
prot_index = {}
for i, row in enumerate(train_df.itertuples()):
prot_index[row.proteins] = i
# BLAST Similarity (Diamond)
diamond_scores = {}
with open(diamond_scores_file) as f:
for line in f:
it = line.strip().split()
if it[0] not in diamond_scores:
diamond_scores[it[0]] = {}
diamond_scores[it[0]][it[1]] = float(it[2])
blast_preds = []
for i, row in enumerate(valid_df.itertuples()):
annots = {}
prot_id = row.proteins
# BlastKNN
if prot_id in diamond_scores:
sim_prots = diamond_scores[prot_id]
allgos = set()
total_score = 0.0
for p_id, score in sim_prots.items():
allgos |= annotations[prot_index[p_id]]
total_score += score
allgos = list(sorted(allgos))
sim = np.zeros(len(allgos), dtype=np.float32)
for j, go_id in enumerate(allgos):
s = 0.0
for p_id, score in sim_prots.items():
if go_id in annotations[prot_index[p_id]]:
s += score
sim[j] = s / total_score
ind = np.argsort(-sim)
for go_id, score in zip(allgos, sim):
annots[go_id] = score
blast_preds.append(annots)
# DeepGOPlus
go_set = go_rels.get_namespace_terms(NAMESPACES[ont])
go_set.remove(FUNC_DICT[ont])
labels = valid_df['annotations'].values
labels = list(map(lambda x: set(filter(lambda y: y in go_set, x)), labels))
print(len(go_set))
best_fmax = 0.0
best_alpha = 0.0
for alpha in range(44, 70):
alpha /= 100.0
deep_preds = []
for i, row in enumerate(valid_df.itertuples()):
annots_dict = blast_preds[i].copy()
for go_id in annots_dict:
annots_dict[go_id] *= alpha
for j, score in enumerate(row.preds):
go_id = terms[j]
score *= 1 - alpha
if go_id in annots_dict:
annots_dict[go_id] += score
else:
annots_dict[go_id] = score
deep_preds.append(annots_dict)
fmax = 0.0
tmax = 0.0
precisions = []
recalls = []
smin = 1000000.0
rus = []
mis = []
for t in range(14, 20):
threshold = t / 100.0
preds = []
for i, row in enumerate(valid_df.itertuples()):
annots = set()
for go_id, score in deep_preds[i].items():
if score >= threshold:
annots.add(go_id)
new_annots = set()
for go_id in annots:
new_annots |= go_rels.get_anchestors(go_id)
preds.append(new_annots)
# Filter classes
preds = list(
map(lambda x: set(filter(lambda y: y in go_set, x)), preds))
fscore, prec, rec, s, ru, mi, fps, fns = evaluate_annotations(
go_rels, labels, preds)
avg_fp = sum(map(lambda x: len(x), fps)) / len(fps)
avg_ic = sum(
map(lambda x: sum(map(lambda go_id: go_rels.get_ic(go_id), x)),
fps)) / len(fps)
print(
f'Fscore: {fscore}, Precision: {prec}, Recall: {rec} S: {s}, RU: {ru}, MI: {mi} threshold: {threshold}'
)
if fmax < fscore:
fmax = fscore
tmax = threshold
if smin > s:
smin = s
if best_fmax < fmax:
best_fmax = fmax
best_alpha = alpha
print(
f'Alpha: {alpha} Fmax: {fmax:0.3f}, Smin: {smin:0.3f}, threshold: {tmax}'
)
print(f'{best_alpha} {best_fmax}')
def main(benchmark_file, train_data_file, hpo_file, terms_file, root_class):
hp = Ontology(hpo_file, with_rels=True)
terms_df = pd.read_pickle(terms_file)
terms = terms_df['terms'].values.flatten()
terms_dict = {v: i for i, v in enumerate(terms)}
noknowledge_prots = set()
with open('data-cafa/noknowledge_targets.txt') as f:
for line in f:
noknowledge_prots.add(line.strip())
bench_annots = {}
with open(benchmark_file) as f:
for line in f:
it = line.strip().split('\t')
t_id = it[0]
if t_id not in noknowledge_prots:
continue
hp_id = it[1]
if t_id not in bench_annots:
bench_annots[t_id] = set()
bench_annots[t_id] |= hp.get_anchestors(hp_id)
train_df = pd.read_pickle(train_data_file)
naive_annots = {}
for i, row in train_df.iterrows():
for hp_id in row.hp_annotations:
if hp_id in naive_annots:
naive_annots[hp_id] += 1
else:
naive_annots[hp_id] = 1
for hp_id in naive_annots:
naive_annots[hp_id] /= 1.0 * len(train_df)
annotations = train_df['hp_annotations'].values
annotations = list(map(lambda x: set(x), annotations))
hp.calculate_ic(annotations)
hp_set = set(terms)
all_classes = hp.get_term_set(root_class)
hp_set = hp_set.intersection(all_classes)
hp_set.discard(root_class)
print(len(hp_set))
labels = []
for t_id, hps in bench_annots.items():
labels.append(hps)
labels = list(map(lambda x: set(filter(lambda y: y in hp_set, x)), labels))
# Compute AUC
auc_terms = list(hp_set)
auc_terms_dict = {v: i for i, v in enumerate(auc_terms)}
auc_preds = np.zeros((len(bench_annots), len(hp_set)), dtype=np.float32)
auc_labels = np.zeros((len(bench_annots), len(hp_set)), dtype=np.int32)
for i in range(len(labels)):
for j, hp_id in enumerate(auc_terms):
auc_preds[i, j] = naive_annots[hp_id]
if hp_id in labels[i]:
auc_labels[i, j] = 1
# Compute macro AUROC
roc_auc = 0.0
total = 0
for i, hp_id in enumerate(auc_terms):
if np.sum(auc_labels[:, i]) == 0:
continue
total += 1
auc = compute_roc(auc_labels[:, i], auc_preds[:, i])
if not math.isnan(auc):
roc_auc += auc
else:
roc_auc += 1
roc_auc /= total
print(roc_auc)
return
fmax = 0.0
tmax = 0.0
pmax = 0.0
rmax = 0.0
precisions = []
recalls = []
smin = 1000000.0
max_preds = None
for t in range(0, 101):
threshold = t / 100.0
annots = set()
for hp_id, score in naive_annots.items():
if score >= threshold:
annots.add(hp_id)
new_annots = set()
for hp_id in annots:
new_annots |= hp.get_anchestors(hp_id)
preds = []
for t_id, hps in bench_annots.items():
preds.append(new_annots)
fscore, prec, rec, s = evaluate_annotations(hp, labels, preds)
precisions.append(prec)
recalls.append(rec)
print(f'Fscore: {fscore}, S: {s}, threshold: {threshold}')
if fmax < fscore:
fmax = fscore
pmax = prec
rmax = rec
tmax = threshold
max_preds = preds
if smin > s:
smin = s
precisions = np.array(precisions)
recalls = np.array(recalls)
sorted_index = np.argsort(recalls)
recalls = recalls[sorted_index]
precisions = precisions[sorted_index]
aupr = np.trapz(precisions, recalls)
print(
f'AUROC: {roc_auc:0.3f}, AUPR: {aupr:0.3f}, Fmax: {fmax:0.3f}, Prec: {pmax:0.3f}, Rec: {rmax:0.3f}, Smin: {smin:0.3f}, threshold: {tmax}'
)
def main(train_data_file, test_data_file, terms_file, rules_file):
hp = Ontology('data/hp.obo', with_rels=True)
terms_df = pd.read_pickle(terms_file)
terms = terms_df['terms'].values.flatten()
terms_dict = {v: i for i, v in enumerate(terms)}
train_df = pd.read_pickle(train_data_file)
rule_annots = {}
with open(rules_file) as f:
for line in f:
it = line.strip().split()
go_id = it[0].replace('_', ':')
hp_id = it[1].replace('_', ':')
if go_id not in rule_annots:
rule_annots[go_id] = set()
rule_annots[go_id].add(hp_id)
test_df = pd.read_pickle(test_data_file)
annotations = train_df['hp_annotations'].values
annotations = list(map(lambda x: set(x), annotations))
test_annotations = test_df['hp_annotations'].values
test_annotations = list(map(lambda x: set(x), test_annotations))
hp.calculate_ic(annotations)
hp_set = set(terms)
hp_set_anch = set()
for hp_id in hp_set:
hp_set_anch |= hp.get_anchestors(hp_id)
labels = test_annotations
# labels = list(map(lambda x: set(filter(lambda y: y in hp_set_anch, x)), labels))
fmax = 0.0
tmax = 0.0
precisions = []
recalls = []
smin = 1000000.0
max_preds = None
for t in range(0, 101):
threshold = t / 100.0
preds = []
for i, row in enumerate(test_df.itertuples()):
gene_id = row.genes
annots = set()
for item in row.deepgo_annotations:
go_id, score = item.split('|')
score = float(score)
if score >= threshold and go_id in rule_annots:
annots |= rule_annots[go_id]
new_annots = set()
for hp_id in annots:
new_annots |= hp.get_anchestors(hp_id)
preds.append(new_annots)
# Filter classes
fscore, prec, rec, s = evaluate_annotations(hp, labels, preds)
precisions.append(prec)
recalls.append(rec)
print(f'Fscore: {fscore}, S: {s}, threshold: {threshold}')
if fmax < fscore:
fmax = fscore
tmax = threshold
max_preds = preds
if smin > s:
smin = s
print(f'Fmax: {fmax:0.3f}, Smin: {smin:0.3f}, threshold: {tmax}')
test_df['hp_preds'] = max_preds
test_df.to_pickle('data/predictions_max.pkl')
precisions = np.array(precisions)
recalls = np.array(recalls)
sorted_index = np.argsort(recalls)
recalls = recalls[sorted_index]
precisions = precisions[sorted_index]
aupr = np.trapz(precisions, recalls)
print(f'AUPR: {aupr:0.3f}')
def main(train_data_file, preds_file, ont):
go = Ontology('data/go.obo', with_rels=True)
terms_df = pd.read_pickle('data-deepgo/' + ont + '.pkl')
terms = terms_df['functions'].values.flatten()
terms_dict = {v: i for i, v in enumerate(terms)}
train_df = pd.read_pickle(train_data_file)
annotations = train_df['annotations'].values
annotations = list(map(lambda x: set(x), annotations))
test_df = pd.read_pickle(preds_file)
# Annotations
test_annotations = []
for i, row in enumerate(test_df.itertuples()):
annots = set()
for go_id in row.gos:
if go.has_term(go_id):
annots |= go.get_anchestors(go_id)
test_annotations.append(annots)
go.calculate_ic(annotations + test_annotations)
prot_index = {}
for i, row in enumerate(train_df.itertuples()):
prot_index[row.proteins] = i
# DeepGO
go_set = go.get_namespace_terms(NAMESPACES[ont])
go_set.remove(FUNC_DICT[ont])
labels = test_annotations
labels = list(map(lambda x: set(filter(lambda y: y in go_set, x)), labels))
print(len(go_set))
fmax = 0.0
tmax = 0.0
smin = 1000.0
precisions = []
recalls = []
for threshold in np.arange(0.005, 1, .01):
# threshold = t / 100.0
preds = []
for i, row in enumerate(test_df.itertuples()):
annots = set()
for j, score in enumerate(row.predictions):
if score >= threshold:
annots.add(terms[j])
new_annots = set()
for go_id in annots:
new_annots |= go.get_anchestors(go_id)
preds.append(new_annots)
# Filter classes
preds = list(
map(lambda x: set(filter(lambda y: y in go_set, x)), preds))
fscore, prec, rec, s = evaluate_annotations(go, labels, preds)
precisions.append(prec)
recalls.append(rec)
print(f'Fscore: {fscore}, S: {s}, threshold: {threshold}')
if fmax < fscore:
fmax = fscore
tmax = threshold
if smin > s:
smin = s
print(f'Fmax: {fmax:0.3f}, Smin: {smin:0.3f}, threshold: {tmax}')
precisions = np.array(precisions)
recalls = np.array(recalls)
sorted_index = np.argsort(recalls)
recalls = recalls[sorted_index]
precisions = precisions[sorted_index]
aupr = np.trapz(precisions, recalls)
print(f'AUPR: {aupr:0.3f}')
plt.figure()
lw = 2
plt.plot(recalls,
precisions,
color='darkorange',
lw=lw,
label=f'AUPR curve (area = {aupr:0.3f})')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('Recall')
plt.ylabel('Precision')
plt.title('Area Under the Precision-Recall curve')
plt.legend(loc="lower right")
plt.savefig('aupr.pdf')
plt.show()
def main(go_file, train_sequences_file, train_annotations_file,
test_sequences_file, test_annotations_file, out_terms_file,
train_data_file, test_data_file, min_count):
logging.info('Loading GO')
go = Ontology(go_file, with_rels=True)
logging.info('Loading training annotations')
train_annots = {}
with open(train_annotations_file, 'r') as f:
for line in f:
it = line.strip().split('\t')
prot_id = it[0]
if prot_id not in train_annots:
train_annots[prot_id] = set()
go_id = it[1]
train_annots[prot_id].add(go_id)
logging.info('Loading training sequences')
info, seqs = read_fasta(train_sequences_file)
proteins = []
sequences = []
annotations = []
for prot_info, sequence in zip(info, seqs):
prot_id = prot_info.split()[0]
if prot_id in train_annots:
proteins.append(prot_id)
sequences.append(sequence)
annotations.append(train_annots[prot_id])
prop_annotations = []
cnt = Counter()
for annots in annotations:
# Propagate annotations
annots_set = set()
for go_id in annots:
annots_set |= go.get_anchestors(go_id)
prop_annotations.append(annots_set)
for go_id in annots_set:
cnt[go_id] += 1
df = pd.DataFrame({
'proteins': proteins,
'sequences': sequences,
'annotations': prop_annotations,
})
logging.info(f'Train proteins: {len(df)}')
logging.info(f'Saving training data to {train_data_file}')
df.to_pickle(train_data_file)
# Filter terms with annotations more than min_count
res = {}
for key, val in cnt.items():
if val >= min_count:
ont = key.split(':')[0]
if ont not in res:
res[ont] = []
res[ont].append(key)
terms = []
for key, val in res.items():
terms += val
logging.info(f'Number of terms {len(terms)}')
logging.info(f'Saving terms to {out_terms_file}')
df = pd.DataFrame({'terms': terms})
df.to_pickle(out_terms_file)
logging.info('Loading testing annotations')
test_annots = {}
with open(test_annotations_file, 'r') as f:
for line in f:
it = line.strip().split('\t')
prot_id = it[0]
if prot_id not in test_annots:
test_annots[prot_id] = set()
go_id = it[1]
test_annots[prot_id].add(go_id)
logging.info('Loading testing sequences')
info, seqs = read_fasta(test_sequences_file)
proteins = []
sequences = []
annotations = []
for prot_info, sequence in zip(info, seqs):
prot_id = prot_info.split()[0]
if prot_id in test_annots:
proteins.append(prot_id)
sequences.append(sequence)
annotations.append(test_annots[prot_id])
prop_annotations = []
for annots in annotations:
# Propagate annotations
annots_set = set()
for go_id in annots:
annots_set |= go.get_anchestors(go_id)
prop_annotations.append(annots_set)
df = pd.DataFrame({
'proteins': proteins,
'sequences': sequences,
'annotations': prop_annotations,
})
logging.info(f'Test proteins {len(df)}')
logging.info(f'Saving testing data to {test_data_file}')
df.to_pickle(test_data_file)
def main(train_data_file, test_data_file, terms_file, diamond_scores_file, ont,
alpha):
alpha /= 100.0
mp = Ontology('data/mp.obo', with_rels=True)
terms_df = pd.read_pickle(terms_file)
terms = terms_df['terms'].values.flatten()
terms_dict = {v: i for i, v in enumerate(terms)}
train_df = pd.read_pickle(train_data_file)
test_df = pd.read_pickle(test_data_file)
annotations = train_df['mp_annotations'].values
annotations = list(map(lambda x: set(x), annotations))
test_annotations = test_df['mp_annotations'].values
test_annotations = list(map(lambda x: set(x), test_annotations))
mp.calculate_ic(annotations)
prot_index = {}
for i, row in enumerate(train_df.itertuples()):
prot_index[row.proteins] = i
# GO2HP preds
rules = {}
with open('data/go2hp.txt') as f:
for line in f:
it = line.strip().split('\t')
go_id = it[0].replace('_', ':')
mp_ids = list(map(lambda x: x.replace('_', ':'), it[1:]))
if go_id not in rules:
rules[go_id] = []
rules[go_id] = mp_ids
pheno2go_preds = {}
for i, row in enumerate(test_df.itertuples()):
prot_id = row.proteins
if prot_id not in pheno2go_preds:
pheno2go_preds[prot_id] = {}
for item in row.deepgo_annotations:
go_id, score = item.split('|')
if go_id in rules:
for mp_id in rules[go_id]:
pheno2go_preds[prot_id][mp_id] = max(
float(score), pheno2go_preds[prot_id].get(mp_id, 0))
labels = test_annotations
fmax = 0.0
tmax = 0.0
precisions = []
recalls = []
smin = 1000000.0
for t in range(101):
threshold = t / 100.0
preds = []
for i, row in enumerate(test_df.itertuples()):
prot_id = row.proteins
annots_dict = {} #pheno2go_preds[prot_id]
for j, score in enumerate(row.preds):
mp_id = terms[j]
annots_dict[mp_id] = max(score, annots_dict.get(mp_id, 0))
annots = set()
for mp_id, score in annots_dict.items():
if score >= threshold:
annots.add(mp_id)
new_annots = set()
for mp_id in annots:
new_annots |= mp.get_anchestors(mp_id)
preds.append(new_annots)
# Filter classes
fscore, prec, rec, s = evaluate_annotations(mp, labels, preds)
precisions.append(prec)
recalls.append(rec)
print(f'Fscore: {fscore}, S: {s}, threshold: {threshold}')
if fmax < fscore:
fmax = fscore
tmax = threshold
if smin > s:
smin = s
print(f'Fmax: {fmax:0.3f}, Smin: {smin:0.3f}, threshold: {tmax}')
precisions = np.array(precisions)
recalls = np.array(recalls)
sorted_index = np.argsort(recalls)
recalls = recalls[sorted_index]
precisions = precisions[sorted_index]
aupr = np.trapz(precisions, recalls)
print(f'AUPR: {aupr:0.3f}')
plt.figure()
lw = 2
plt.plot(recalls,
precisions,
color='darkorange',
lw=lw,
label=f'AUPR curve (area = {aupr:0.2f})')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('Recall')
plt.ylabel('Precision')
plt.title('Area Under the Precision-Recall curve')
plt.legend(loc="lower right")
plt.savefig(f'aupr_{ont}_{alpha:0.2f}.pdf')
df = pd.DataFrame({'precisions': precisions, 'recalls': recalls})
df.to_pickle(f'PR_{ont}_{alpha:0.2f}.pkl')
def main(in_file, out_file, go_file, model_file, terms_file, annotations_file,
chunk_size, diamond_file, threshold, batch_size, alpha):
# Load GO and read list of all terms
go = Ontology(go_file, with_rels=True)
terms_df = pd.read_pickle(terms_file)
terms = terms_df['terms'].values.flatten()
# Read known experimental annotations
annotations = {}
df = pd.read_pickle(annotations_file)
for row in df.itertuples():
annotations[row.proteins] = set(row.prop_annotations)
go.calculate_ic(annotations.values())
diamond_preds = {}
mapping = {}
with gzip.open(diamond_file, 'rt') as f:
for line in f:
it = line.strip().split()
if it[0] not in mapping:
mapping[it[0]] = {}
mapping[it[0]][it[1]] = float(it[2])
for prot_id, sim_prots in mapping.items():
annots = {}
allgos = set()
total_score = 0.0
for p_id, score in sim_prots.items():
allgos |= annotations[p_id]
total_score += score
allgos = list(sorted(allgos))
sim = np.zeros(len(allgos), dtype=np.float32)
for j, go_id in enumerate(allgos):
s = 0.0
for p_id, score in sim_prots.items():
if go_id in annotations[p_id]:
s += score
sim[j] = s / total_score
for go_id, score in zip(allgos, sim):
annots[go_id] = score
diamond_preds[prot_id] = annots
# Load CNN model
model = load_model(model_file)
# Alphas for the latest model
alphas = {NAMESPACES['mf']: 0.55, NAMESPACES['bp']: 0.59, NAMESPACES['cc']: 0.46}
# Alphas for the cafa2 model
# alphas = {NAMESPACES['mf']: 0.63, NAMESPACES['bp']: 0.68, NAMESPACES['cc']: 0.48}
start_time = time.time()
total_seq = 0
w = gzip.open(out_file, 'wt')
for prot_ids, sequences in read_fasta(in_file, chunk_size):
total_seq += len(prot_ids)
deep_preds = {}
ids, data = get_data(sequences)
preds = model.predict(data, batch_size=batch_size)
assert preds.shape[1] == len(terms)
for i, j in enumerate(ids):
prot_id = prot_ids[j]
if prot_id not in deep_preds:
deep_preds[prot_id] = {}
for l in range(len(terms)):
if preds[i, l] >= 0.01: # Filter out very low scores
if terms[l] not in deep_preds[prot_id]:
deep_preds[prot_id][terms[l]] = preds[i, l]
else:
deep_preds[prot_id][terms[l]] = max(
deep_preds[prot_id][terms[l]], preds[i, l])
# Combine diamond preds and deepgo
for prot_id in prot_ids:
annots = {}
if prot_id in diamond_preds:
for go_id, score in diamond_preds[prot_id].items():
annots[go_id] = score * alphas[go.get_namespace(go_id)]
for go_id, score in deep_preds[prot_id].items():
if go_id in annots:
annots[go_id] += (1 - alphas[go.get_namespace(go_id)]) * score
else:
annots[go_id] = (1 - alphas[go.get_namespace(go_id)]) * score
# Propagate scores with ontology structure
gos = list(annots.keys())
for go_id in gos:
for g_id in go.get_anchestors(go_id):
if g_id in annots:
annots[g_id] = max(annots[g_id], annots[go_id])
else:
annots[g_id] = annots[go_id]
sannots = sorted(annots.items(), key=lambda x: x[1], reverse=True)
for go_id, score in sannots:
if score >= threshold:
w.write(prot_id + '\t' + go_id + '\t' + go.get_term(go_id)['name'] + '\t%.2f' % go.get_ic(go_id) + '\t%.3f\n' % score)
w.write('\n')
w.close()
total_time = time.time() - start_time
print('Total prediction time for %d sequences is %d' % (total_seq, total_time))
def main(go_file, hp_file, hp_annots_file, deepgo_annots_file, data_file,
expressions_file, out_data_file, out_terms_file, min_count):
go = Ontology(go_file, with_rels=True)
print('GO loaded')
hp = Ontology(hp_file, with_rels=True)
print('HP loaded')
iea_annots = {}
go_annots = {}
seqs = {}
df = pd.read_pickle(data_file)
df = df[df['orgs'] == '9606']
acc2prot = {}
name2prot = {}
for i, row in df.iterrows():
accs = row['accessions'].split('; ')
names = row['gene_names']
p_id = row['proteins']
for acc in accs:
acc2prot[acc] = p_id
for name in names:
name = name.upper()
if name not in name2prot:
name2prot[name] = set()
name2prot[name].add(p_id)
if p_id not in go_annots:
go_annots[p_id] = set()
if p_id not in iea_annots:
iea_annots[p_id] = set()
go_annots[p_id] |= set(row.exp_annotations)
iea_annots[p_id] |= set(row.iea_annotations)
seqs[p_id] = row.sequences
print('GO Annotations', len(go_annots))
print('Loading HP annotations')
hp_annots = {}
unrev = set()
with open(hp_annots_file) as f:
next(f)
for line in f:
it = line.strip().split('\t')
acc_id = it[0]
hp_id = it[1]
if acc_id not in acc2prot:
unrev.add(acc_id)
continue
p_id = acc2prot[acc_id]
if p_id not in hp_annots:
hp_annots[p_id] = set()
if hp.has_term(hp_id):
hp_annots[p_id] |= hp.get_anchestors(hp_id)
print('HP Annotations', len(hp_annots))
dg_annots = {}
gos = set()
with open(deepgo_annots_file) as f:
for line in f:
it = line.strip().split('\t')
p_id = it[0]
annots = dg_annots.get(p_id, {})
for item in it[1:]:
go_id, score = item.split('|')
score = float(score)
annots[go_id] = max(score, annots.get(go_id, 0))
dg_annots[p_id] = annots
gos |= set(annots.keys())
print('DeepGO Annotations', len(dg_annots))
deepgo_annots = {}
for g_id, annots in dg_annots.items():
deepgo_annots[g_id] = [
go_id + '|' + str(score) for go_id, score in annots.items()
]
print('Number of GOs', len(gos))
df = pd.DataFrame({'gos': list(gos)})
#df.to_pickle('data-cafa/gos.pkl')
logging.info('Processing annotations')
cnt = Counter()
annotations = list()
for p_id, annots in hp_annots.items():
for term in annots:
cnt[term] += 1
gene_exp = {}
max_val = 0
with open(expressions_file) as f:
for line in f:
if line.startswith('#') or line.startswith('Gene'):
continue
it = line.strip().split('\t')
gene_name = it[1].upper()
if gene_name in name2prot:
exp = np.zeros((53, ), dtype=np.float32)
for i in range(len(it[2:])):
exp[i] = float(it[2 + i]) if it[2 + i] != '' else 0.0
for p_id in name2prot[gene_name]:
gene_exp[p_id] = exp / np.max(exp)
print('Expression values', len(gene_exp))
deepgo_annotations = []
go_annotations = []
iea_annotations = []
hpos = []
proteins = []
sequences = []
expressions = []
mis_exp = 0
for p_id, phenos in hp_annots.items():
if p_id not in dg_annots:
continue
proteins.append(p_id)
hpos.append(phenos)
go_annotations.append(go_annots[p_id])
iea_annotations.append(iea_annots[p_id])
deepgo_annotations.append(deepgo_annots[p_id])
sequences.append(seqs[p_id])
if p_id in gene_exp:
expressions.append(gene_exp[p_id])
else:
expressions.append(np.zeros((53, ), dtype=np.float32))
mis_exp += 1
print('Missing expressions', mis_exp)
df = pd.DataFrame({
'proteins': proteins,
'hp_annotations': hpos,
'go_annotations': go_annotations,
'iea_annotations': iea_annotations,
'deepgo_annotations': deepgo_annotations,
'sequences': sequences,
'expressions': expressions
})
df.to_pickle(out_data_file)
print(f'Number of proteins {len(df)}')
test_annots = {}
tar2prot = {}
with open('data-cafa/tar2prot.txt') as f:
for line in f:
it = line[1:].strip().split()
tar2prot[it[0]] = it[1]
unknown_prots = set()
with open('data-cafa/benchmark/groundtruth/leafonly_HPO.txt') as f:
for line in f:
it = line.strip().split()
p_id = tar2prot[it[0]]
if p_id in hp_annots:
continue
unknown_prots.add(it[0])
hp_id = it[1]
if p_id not in test_annots:
test_annots[p_id] = set()
if hp.has_term(hp_id):
test_annots[p_id] |= hp.get_anchestors(hp_id)
with open('data-cafa/noknowledge_targets.txt', 'w') as f:
for t_id in unknown_prots:
f.write(t_id + '\n')
deepgo_annotations = []
go_annotations = []
iea_annotations = []
hpos = []
proteins = []
sequences = []
expressions = []
mis_exp = 0
for p_id, phenos in test_annots.items():
if p_id not in dg_annots:
continue
proteins.append(p_id)
hpos.append(phenos)
go_annotations.append(go_annots[p_id])
iea_annotations.append(iea_annots[p_id])
deepgo_annotations.append(deepgo_annots[p_id])
sequences.append(seqs[p_id])
if p_id in gene_exp:
expressions.append(gene_exp[p_id])
else:
expressions.append(np.zeros((53, ), dtype=np.float32))
mis_exp += 1
df = pd.DataFrame({
'proteins': proteins,
'hp_annotations': hpos,
'go_annotations': go_annotations,
'iea_annotations': iea_annotations,
'deepgo_annotations': deepgo_annotations,
'sequences': sequences,
'expressions': expressions
})
print('Missing expressions test', mis_exp)
df.to_pickle('data-cafa/human_test.pkl')
print(f'Number of test proteins {len(df)}')
# Filter terms with annotations more than min_count
terms_set = set()
all_terms = []
for key, val in cnt.items():
if key == 'HP:0000001':
continue
all_terms.append(key)
if val >= min_count:
terms_set.add(key)
terms = []
for t_id in hp.get_ordered_terms():
if t_id in terms_set:
terms.append(t_id)
logging.info(f'Number of terms {len(terms)}')